From 8216ba599b6c33207f413381b755d8db25c01440 Mon Sep 17 00:00:00 2001 From: Ines Montani Date: Thu, 5 Jan 2017 18:11:04 +0100 Subject: [PATCH] Add tests for longer and mixed English texts --- spacy/tests/en/tokenizer/test_text.py | 36 +++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) create mode 100644 spacy/tests/en/tokenizer/test_text.py diff --git a/spacy/tests/en/tokenizer/test_text.py b/spacy/tests/en/tokenizer/test_text.py new file mode 100644 index 000000000..c7178fbf9 --- /dev/null +++ b/spacy/tests/en/tokenizer/test_text.py @@ -0,0 +1,36 @@ +# coding: utf-8 +"""Test that longer and mixed texts are tokenized correctly.""" + + +from __future__ import unicode_literals + +import pytest + + +def test_tokenizer_handles_long_text(en_tokenizer): + text = """Tributes pour in for late British Labour Party leader + +Tributes poured in from around the world Thursday +to the late Labour Party leader John Smith, who died earlier from a massive +heart attack aged 55. + +In Washington, the US State Department issued a statement regretting "the +untimely death" of the rapier-tongued Scottish barrister and parliamentarian. + +"Mr. Smith, throughout his distinguished""" + tokens = en_tokenizer(text) + assert len(tokens) == 76 + + +@pytest.mark.parametrize('text,length', [ + ("The U.S. Army likes Shock and Awe.", 8), + ("U.N. regulations are not a part of their concern.", 10), + ("“Isn't it?”", 6), + ("""Yes! "I'd rather have a walk", Ms. Comble sighed. """, 15), + ("""'Me too!', Mr. P. Delaware cried. """, 11), + ("They ran about 10km.", 6), + # ("But then the 6,000-year ice age came...", 10) + ]) +def test_tokenizer_handles_cnts(en_tokenizer, text, length): + tokens = en_tokenizer(text) + assert len(tokens) == length